Anthropic
Previous flagship Claude Opus release retained for compatibility after the Claude Opus 4.7 launch. Still strong for advanced reasoning, extended thinking, computer use, and coding, but superseded by Opus 4.7 for Anthropic's latest top-end performance.
Previous flagship Claude Opus release retained for compatibility after the Claude Opus 4.7 launch.
60.3
Quality Score
1293
Arena ELO
Undisclosed
Parameters
200K
Context
Sign in to join the discussion
0
Downloads
0
Likes
Dec 2025
Released
Launches
1
Pricing
1
Benchmarks
18
API
1
Research
2
General
7
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your security controls applied by default. https://t.co/cxvmk3feHp
View source
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
SWE-Bench Verified resolved rate 75.6
We’re partnering with the Gates Foundation, committing $200 million in grants, Claude credits, and technical support to programs in global health, life sciences, education, agriculture, and economic mobility. Read more: https://t.co/eqCrLKtNCq
View sourceSWE-Bench Verified resolved rate 75.6
View sourceLiveCodeBench pass@1 62.4 across 1055 tasks
View sourceQuality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
View source
Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your security controls applied by default. https://t.co/cxvmk3feHp
We’re partnering with the Gates Foundation, committing $200 million in grants, Claude credits, and technical support to programs in global health, life sciences, education, agriculture, and economic mobility. Read more: https://t.co/eqCrLKtNCq
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Quality: 92/100 | Speed: 40/100 | Price: $15/M tokens | MMLU: 91.5% | HumanEval: 92.5%
Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification.
Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce , a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.
LiveCodeBench pass@1 62.4 across 1055 tasks